forest-claude-tools

A marketplace listing for four Claude plugins covering HTTP API clients, Tidewave tools, web testing, and session handoffs.

In plain words
What is it for?
It helps discover tools for building Elixir API clients, using Tidewave with Elixir or Phoenix, testing web pages, and summarizing sessions for handoff.
Why use it?
It groups several developer-workflow add-ons in one place instead of requiring each plugin to be found separately.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add forest/agent-skills
agentmods
npx agentmods add plugins/forest/agent-skills/marketplace
Clone the repo
git clone --depth 1 https://github.com/forest/agent-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

forest-claude-tools scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 36 lines

What it actually says

{
  "name": "forest-claude-tools",
  "owner": {
    "name": "forest"
  },
  "metadata": {
    "description": "Opinionated skills for improving daily work efficiency with Claude"
  },
  "plugins": [
    {
      "name": "req-api-client",
      "source": "./plugins/req-api-client",
      "description": "Build HTTP API clients and SDK wrappers using Elixir's Req library",
      "version": "1.0.0"
    },
    {
      "name": "tidewave-tools-usage",
      "source": "./plugins/tidewave-tools-usage",
      "description": "Prioritize Tidewave MCP tools for Elixir/Phoenix development",
      "version": "1.0.0"
    },
    {
      "name": "web-cli",
      "source": "./plugins/web-cli",
      "description": "Web browser CLI for testing and verifying web pages during development",
      "version": "1.0.0"
    },
    {
      "name": "session-handoff",
      "source": "./plugins/session-handoff",
      "description": "Generates deterministic session summaries for handoff between Claude sessions — preserves decisions, rationale, and rejected options without auto-compact inference",
      "version": "1.0.0"
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 36 lines scan A 39d79c895dd9

Subscribe to this mod's changes

forest-claude-tools is a plugin published in the GitHub repository forest/agent-skills (2 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.